diff --git a/model_zoo/official/rl/dqn/README.md b/model_zoo/official/rl/dqn/README.md index 5731d24741b..bd8b165de3c 100644 --- a/model_zoo/official/rl/dqn/README.md +++ b/model_zoo/official/rl/dqn/README.md @@ -34,8 +34,8 @@ The overall network architecture of DQN is show below: - Framework - [MindSpore](https://www.mindspore.cn/install/en) - For more information, please check the resources below： - - [MindSpore Tutorials](https://www.mindspore.cn/tutorial/training/en/master/index.html) - - [MindSpore Python API](https://www.mindspore.cn/doc/api_python/en/master/index.html) + - [MindSpore Tutorials](https://www.mindspore.cn/tutorials/en/master/index.html) + - [MindSpore Python API](https://www.mindspore.cn/docs/api/en/master/index.html) - third-party libraries @@ -118,7 +118,7 @@ pip install gym | Loss Function | MSELoss |MSELoss | | outputs | Reward | Reward | | Params (M) | 7.3k | 7.3k | -| Scripts | https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/rl/dqn | https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/rl/dqn | +| Scripts | <<>> | https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/rl/dqn | ## [Description of Random Situation](#content) @@ -126,4 +126,4 @@ We use random seed in train.py. ## [ModeZoo Homepage](#contents) -Please check the official [homepage](https://gitee.com/mindspore/mindspore/tree/master/model_zoo). \ No newline at end of file +Please check the official [homepage](https://gitee.com/mindspore/mindspore/tree/master/model_zoo). diff --git a/model_zoo/official/rl/dqn/README_CN.md b/model_zoo/official/rl/dqn/README_CN.md index 6fca820d493..8e014d50cd5 100644 --- a/model_zoo/official/rl/dqn/README_CN.md +++ b/model_zoo/official/rl/dqn/README_CN.md @@ -35,10 +35,10 @@ DQN网络的模型结构见论文： - 硬件 - Ascend或GPU处理器 - 框架 - - [MindSpore](https://www.mindspore.cn/install/en) + - [MindSpore](https://www.mindspore.cn/install/) - 通过下面网址可以获得更多信息： - - [MindSpore Tutorials](https://www.mindspore.cn/tutorial/training/en/master/index.html) - - [MindSpore Python API](https://www.mindspore.cn/doc/api_python/en/master/index.html) + - [MindSpore Tutorials](https://www.mindspore.cn/tutorials/zh-CN/master/index.html) + - [MindSpore Python API](https://www.mindspore.cn/docs/api/zh-CN/master/index.html) - 第三方库 @@ -115,7 +115,7 @@ pip install gym | 损失函数 | MSELoss | MSELoss | | 输出 | 游戏得分值 | 游戏得分值 | | 参数量(M) | 7.3k | 7.3k | -| 脚本 | https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/rl/dqn | https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/rl/dqn | +| 脚本 | <<<>>> | https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/rl/dqn | # 随机情况描述 diff --git a/model_zoo/research/cv/ICNet/README.md b/model_zoo/research/cv/ICNet/README.md index 8b330c1d874..de7842d4787 100644 --- a/model_zoo/research/cv/ICNet/README.md +++ b/model_zoo/research/cv/ICNet/README.md @@ -42,8 +42,8 @@ It contains 5,000 finely annotated images split into training, validation and te - frame: - [Mindspore](https://www.mindspore.cn/install) - For details, please refer to the following resources: - - [MindSpore course](https://www.mindspore.cn/tutorial/training/zh-CN/master/index.html) - - [MindSpore Python API](https://www.mindspore.cn/doc/api_python/zh-CN/master/index.html) + - [MindSpore course](https://www.mindspore.cn/tutorials/en/master/index.html) + - [MindSpore Python API](https://www.mindspore.cn/docs/api/zh-CN/master/index.html) # [Scription Description](#Content) diff --git a/model_zoo/research/cv/LightCNN/README_CN.md b/model_zoo/research/cv/LightCNN/README_CN.md index 2109793ac33..b7dc957f487 100644 --- a/model_zoo/research/cv/LightCNN/README_CN.md +++ b/model_zoo/research/cv/LightCNN/README_CN.md @@ -103,11 +103,11 @@ LightCNN适用于有大量噪声的人脸识别数据集，提出了maxout 的 - 框架 - [MindSpore](https://www.mindspore.cn/install) - 如需查看详情，请参见如下资源： - - [MindSpore教程](https://www.mindspore.cn/tutorial/training/zh-CN/master/index.html) - - [MindSpore Python API](https://www.mindspore.cn/doc/api_python/zh-CN/master/index.html) + - [MindSpore教程](https://www.mindspore.cn/tutorials/zh-CN/master/index.html) + - [MindSpore Python API](https://www.mindspore.cn/docs/api/zh-CN/master/index.html) - 生成config json文件用于8卡训练。 - [简易教程](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/utils/hccl_tools) - - 详细配置方法请参照[官网教程](https://www.mindspore.cn/tutorial/training/zh-CN/r1.2/advanced_use/distributed_training_ascend.html#id4)。 + - 详细配置方法请参照[官网教程](https://www.mindspore.cn/tutorials/zh-CN/master/intermediate/distributed_training/distributed_training_ascend.html#id3)。 # 快速入门 @@ -439,7 +439,7 @@ python3 eval_blfur.py \ [3]: https://drive.google.com/file/d/0ByNaVHFekDPRbFg1YTNiMUxNYXc/view?usp=sharing [4]: https://hyper.ai/datasets/5543 [5]: https://pan.baidu.com/s/1eR6vHFO -[6]: https://www.mindspore.cn/tutorial/training/zh-CN/master/advanced_use/enable_mixed_precision.html +[6]: https://www.mindspore.cn/docs/programming_guide/zh-CN/master/enable_mixed_precision.html [7]: http://www.cbsr.ia.ac.cn/users/scliao/projects/blufr/BLUFR.zip [8]: https://github.com/AlfredXiangWu/face_verification_experiment/blob/master/code/lfw_pairs.mat [9]: https://github.com/AlfredXiangWu/face_verification_experiment/blob/master/results/LightenedCNN_B_lfw.mat diff --git a/model_zoo/research/cv/ProtoNet/README.md b/model_zoo/research/cv/ProtoNet/README.md index e424789b6a6..07558b25353 100644 --- a/model_zoo/research/cv/ProtoNet/README.md +++ b/model_zoo/research/cv/ProtoNet/README.md @@ -29,7 +29,7 @@ Proto-Net contains 2 parts named Encoder and Relation. The former one has 4 conv Note that you can run the scripts based on the dataset mentioned in original paper or widely used in relevant domain/network architecture. In the following sections, we will introduce how to run the scripts using the related dataset below. -The dataset omniglot can be obtained from (https://github.com/orobix/Prototypical-Networks-for-Few-shot-Learning-PyTorch/blob/master/). You can obtain the dataset after running the scripts. +The dataset omniglot can be obtained from (). You can obtain the dataset after running the scripts. ```bash cd src @@ -65,8 +65,8 @@ python train.py - Framework - [MindSpore](https://www.mindspore.cn/install/en) - For more information, please check the resources below： - - [MindSpore Tutorials](https://www.mindspore.cn/tutorials/en/master/index.html) - - [MindSpore Python API](https://www.mindspore.cn/docs/api/en/master/index.html) + - [MindSpore Tutorials](https://www.mindspore.cn/tutorials/en/master/index.html) + - [MindSpore Python API](https://www.mindspore.cn/docs/api/en/master/index.html) # [Quick Start](#contents) @@ -165,7 +165,7 @@ Test Acc: 0.9954400658607483 Loss: 0.02102319709956646 | Speed | 215 ms/step | | Total time | 3 h 23m (8p) | | Checkpoint for Fine tuning | 440 KB (.ckpt file) | -| Scripts | https://gitee.com/mindspore/mindspore/tree/r1.1/model_zoo/research/cv/protonet | +| Scripts | | # [ModelZoo Homepage](#contents) diff --git a/model_zoo/research/cv/SiamFC/readme.md b/model_zoo/research/cv/SiamFC/README.md similarity index 94% rename from model_zoo/research/cv/SiamFC/readme.md rename to model_zoo/research/cv/SiamFC/README.md index 21026f95241..1624fff7d10 100644 --- a/model_zoo/research/cv/SiamFC/readme.md +++ b/model_zoo/research/cv/SiamFC/README.md @@ -40,12 +40,12 @@ used Dataset :[ILSVRC2015-VID](http://bvisionweb1.cs.unc.edu/ilsvrc2015/ILSVRC20 # [Environmental requirements](#Contents) - Hardware :(Ascend) - - Prepare ascend processor to build hardware environment + - Prepare Ascend processor to build hardware environment - frame: - - [Mindspore](https://www.mindspore.cn/install) + - [Mindspore](https://www.mindspore.cn/install/en) - For details, please refer to the following resources: - - [MindSpore course](https://www.mindspore.cn/tutorial/training/zh-CN/master/index.html) - - [MindSpore Python API](https://www.mindspore.cn/doc/api_python/zh-CN/master/index.html) + - [MindSpore course](https://www.mindspore.cn/tutorials/en/master/index.html) + - [MindSpore Python API](https://www.mindspore.cn/docs/api/en/master/index.html) - more API - got10k toolkit - opencv @@ -191,5 +191,5 @@ Check the checkpoint path used for evaluation before running the following comma |loss function |BCEWithLogits | |training speed | epoch time：285693.557 ms per step time :42.961 ms | |total time |about 5 hours | -|Script URL |https://gitee.com/mindspore/mindspore/tree/master/model_zoo/research/cv/SiamFC | +|Script URL | | |Random number seed |set_seed = 1234 | diff --git a/model_zoo/research/cv/inception_resnet_v2/README.md b/model_zoo/research/cv/inception_resnet_v2/README.md index 950c441243c..f247b8867be 100644 --- a/model_zoo/research/cv/inception_resnet_v2/README.md +++ b/model_zoo/research/cv/inception_resnet_v2/README.md @@ -44,7 +44,7 @@ Dataset used can refer to paper. ## [Mixed Precision(Ascend)](#contents) -The [mixed precision](https://www.mindspore.cn/tutorial/training/en/master/advanced_use/enable_mixed_precision.html) training method accelerates the deep learning neural network training process by using both the single-precision and half-precision data formats, and maintains the network precision achieved by the single-precision training at the same time. Mixed precision training can accelerate the computation process, reduce memory usage, and enable a larger model or batch size to be trained on specific hardware. +The [mixed precision](https://www.mindspore.cn/docs/programming_guide/en/master/enable_mixed_precision.html) training method accelerates the deep learning neural network training process by using both the single-precision and half-precision data formats, and maintains the network precision achieved by the single-precision training at the same time. Mixed precision training can accelerate the computation process, reduce memory usage, and enable a larger model or batch size to be trained on specific hardware. For FP16 operators, if the input data type is FP32, the backend of MindSpore will automatically handle it with reduced precision. Users could check the reduced-precision operators by enabling INFO log and then searching ‘reduce precision’. @@ -210,4 +210,4 @@ In dataset.py, we set the seed inside “create_dataset" function. We also use r # [ModelZoo Homepage](#contents) -Please check the official [homepage](https://gitee.com/mindspore/mindspore/tree/master/model_zoo). \ No newline at end of file +Please check the official [homepage](https://gitee.com/mindspore/mindspore/tree/master/model_zoo). diff --git a/model_zoo/research/cv/inception_resnet_v2/README_CN.md b/model_zoo/research/cv/inception_resnet_v2/README_CN.md index 403d6b9d286..fef05d7a6ac 100644 --- a/model_zoo/research/cv/inception_resnet_v2/README_CN.md +++ b/model_zoo/research/cv/inception_resnet_v2/README_CN.md @@ -28,7 +28,7 @@ Inception_ResNet_v2是Google的深度学习卷积架构系列的一个版本。Inception_ResNet_v2主要通过修改以前的Inception架构来减少计算资源的消耗。该方法在2016年出版的Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning一文中提出的。 -[论文](https://arxiv.org/pdf/1512.00567.pdf)：(https://arxiv.org/pdf/1602.07261.pdf) Christian Szegedy, Sergey Ioffe, Vincent Vanhoucke, Alex Alemi. Computer Vision and Pattern Recognition[J]. 2016. +[论文](https://arxiv.org/pdf/1512.00567.pdf)：() Christian Szegedy, Sergey Ioffe, Vincent Vanhoucke, Alex Alemi. Computer Vision and Pattern Recognition[J]. 2016. # 模型架构 @@ -50,7 +50,7 @@ Inception_ResNet_v2的总体网络架构如下： ## 混合精度（Ascend） -采用[混合精度](https://www.mindspore.cn/tutorial/training/zh-CN/master/advanced_use/enable_mixed_precision.html)的训练方法使用支持单精度和半精度数据来提高深度学习神经网络的训练速度，同时保持单精度训练所能达到的网络精度。混合精度训练提高计算速度、减少内存使用的同时，支持在特定硬件上训练更大的模型或实现更大批次的训练。 +采用[混合精度](https://www.mindspore.cn/docs/programming_guide/zh-CN/master/enable_mixed_precision.html)的训练方法使用支持单精度和半精度数据来提高深度学习神经网络的训练速度，同时保持单精度训练所能达到的网络精度。混合精度训练提高计算速度、减少内存使用的同时，支持在特定硬件上训练更大的模型或实现更大批次的训练。 以FP16算子为例，如果输入数据类型为FP32，MindSpore后台会自动降低精度来处理数据。用户可打开INFO日志，搜索“reduce precision”查看精度降低的算子。 @@ -212,4 +212,3 @@ python export.py --ckpt_file [CKPT_PATH] --device_target [DEVICE_TARGET] --file_ # ModelZoo主页 请浏览官网[主页](https://gitee.com/mindspore/mindspore/tree/master/model_zoo)。 - diff --git a/model_zoo/research/cv/resnext152_64x4d/README.md b/model_zoo/research/cv/resnext152_64x4d/README.md index bdb2992fbdb..f06051c8ba4 100644 --- a/model_zoo/research/cv/resnext152_64x4d/README.md +++ b/model_zoo/research/cv/resnext152_64x4d/README.md @@ -46,18 +46,19 @@ Dataset used: [imagenet](http://www.image-net.org/) ## [Mixed Precision](#contents) -The [mixed precision](https://www.mindspore.cn/tutorial/training/en/master/advanced_use/enable_mixed_precision.html) training method accelerates the deep learning neural network training process by using both the single-precision and half-precision data formats, and maintains the network precision achieved by the single-precision training at the same time. Mixed precision training can accelerate the computation process, reduce memory usage, and enable a larger model or batch size to be trained on specific hardware. +The [mixed precision](https://www.mindspore.cn/docs/programming_guide/en/master/enable_mixed_precision.html) training method accelerates the deep learning neural network training process by using both the single-precision and half-precision data formats, and maintains the network precision achieved by the single-precision training at the same time. Mixed precision training can accelerate the computation process, reduce memory usage, and enable a larger model or batch size to be trained on specific hardware. For FP16 operators, if the input data type is FP32, the backend of MindSpore will automatically handle it with reduced precision. Users could check the reduced-precision operators by enabling INFO log and then searching ‘reduce precision’. # [Environment Requirements](#contents) - Hardware（Ascend） + - Prepare hardware environment with Ascend processor. - Framework - - [MindSpore](https://www.mindspore.cn/install) + - [MindSpore](https://www.mindspore.cn/install/en) - For more information, please check the resources below： - - [MindSpore Tutorials](https://www.mindspore.cn/tutorials/zh-CN/master/index.html) - - [MindSpore Python API](https://www.mindspore.cn/docs/api/zh-CN/master/index.html) + - [MindSpore Tutorials](https://www.mindspore.cn/tutorials/en/master/index.html) + - [MindSpore Python API](https://www.mindspore.cn/docs/api/en/master/index.html) # [Script description](#contents) diff --git a/model_zoo/research/cv/resnext152_64x4d/README_CN.md b/model_zoo/research/cv/resnext152_64x4d/README_CN.md index 2000cc41605..b0ee1604e6e 100644 --- a/model_zoo/research/cv/resnext152_64x4d/README_CN.md +++ b/model_zoo/research/cv/resnext152_64x4d/README_CN.md @@ -51,12 +51,14 @@ ResNeXt整体网络架构如下： ## 混合精度 -采用[混合精度](https://www.mindspore.cn/tutorial/training/zh-CN/master/advanced_use/enable_mixed_precision.html)的训练方法使用支持单精度和半精度数据来提高深度学习神经网络的训练速度，同时保持单精度训练所能达到的网络精度。混合精度训练提高计算速度、减少内存使用的同时，支持在特定硬件上训练更大的模型或实现更大批次的训练。 +采用[混合精度](https://www.mindspore.cn/docs/programming_guide/zh-CN/master/enable_mixed_precision.html)的训练方法使用支持单精度和半精度数据来提高深度学习神经网络的训练速度，同时保持单精度训练所能达到的网络精度。混合精度训练提高计算速度、减少内存使用的同时，支持在特定硬件上训练更大的模型或实现更大批次的训练。 以FP16算子为例，如果输入数据类型为FP32，MindSpore后台会自动降低精度来处理数据。用户可打开INFO日志，搜索“reduce precision”查看精度降低的算子。 # 环境要求 +- 硬件（Ascend） + - 使用Ascend处理器来搭建硬件环境。 - 框架 - [MindSpore](https://www.mindspore.cn/install) - 如需查看详情，请参见如下资源： diff --git a/model_zoo/research/cv/simple_baselines/README.md b/model_zoo/research/cv/simple_baselines/README_CN.md similarity index 93% rename from model_zoo/research/cv/simple_baselines/README.md rename to model_zoo/research/cv/simple_baselines/README_CN.md index fe453b8027c..0a829964656 100644 --- a/model_zoo/research/cv/simple_baselines/README.md +++ b/model_zoo/research/cv/simple_baselines/README_CN.md @@ -53,7 +53,7 @@ simple_baselines的总体网络架构如下： ## 混合精度 -采用[混合精度](https://www.mindspore.cn/tutorial/training/en/master/advanced_use/enable_mixed_precision.html)的训练方法使用支持单精度和半精度数据来提高深度学习神经网络的训练速度，同时保持单精度训练所能达到的网络精度。混合精度训练提高计算速度、减少内存使用的同时，支持在特定硬件上训练更大的模型或实现更大批次的训练。 +采用[混合精度](https://www.mindspore.cn/docs/programming_guide/zh-CN/master/enable_mixed_precision.html))的训练方法使用支持单精度和半精度数据来提高深度学习神经网络的训练速度，同时保持单精度训练所能达到的网络精度。混合精度训练提高计算速度、减少内存使用的同时，支持在特定硬件上训练更大的模型或实现更大批次的训练。 以FP16算子为例，如果输入数据类型为FP32，MindSpore后台会自动降低精度来处理数据。用户可打开INFO日志，搜索“reduce precision”查看精度降低的算子。 # 环境要求 @@ -63,8 +63,8 @@ simple_baselines的总体网络架构如下： - 框架 - [MindSpore](https://www.mindspore.cn/install/en) - 如需查看详情，请参见如下资源： - - [MindSpore教程](https://www.mindspore.cn/tutorial/training/zh-CN/master/index.html) - - [MindSpore Python API](https://www.mindspore.cn/doc/api_python/zh-CN/master/index.html) + - [MindSpore教程](https://www.mindspore.cn/tutorials/zh-CN/master/index.html) + - [MindSpore Python API](https://www.mindspore.cn/docs/api/zh-CN/master/index.html) # 快速入门 diff --git a/model_zoo/research/nlp/seq2seq/README_CN.md b/model_zoo/research/nlp/seq2seq/README_CN.md index 032e7f2404e..7f2a8cd7f51 100644 --- a/model_zoo/research/nlp/seq2seq/README_CN.md +++ b/model_zoo/research/nlp/seq2seq/README_CN.md @@ -33,7 +33,7 @@ bash wmt14_en_fr.sh ## 混合精度 -采用[混合精度](https://www.mindspore.cn/tutorial/training/zh-CN/master/advanced_use/enable_mixed_precision.html)的训练方法使用支持单精度和半精度数据来提高深度学习神经网络的训练速度，同时保持单精度训练所能达到的网络精度。混合精度训练提高计算速度、减少内存使用的同时，支持在特定硬件上训练更大的模型或实现更大批次的训练。 +采用[混合精度](https://www.mindspore.cn/docs/programming_guide/zh-CN/master/enable_mixed_precision.html))的训练方法使用支持单精度和半精度数据来提高深度学习神经网络的训练速度，同时保持单精度训练所能达到的网络精度。混合精度训练提高计算速度、减少内存使用的同时，支持在特定硬件上训练更大的模型或实现更大批次的训练。 以FP16算子为例，如果输入数据类型为FP32，MindSpore后台会自动降低精度来处理数据。用户可打开INFO日志，搜索“reduce precision”查看精度降低的算子。 # 环境要求 @@ -41,10 +41,10 @@ bash wmt14_en_fr.sh - 硬件（Ascend） - 使用Ascend处理器来搭建硬件环境。 - 框架 - - [MindSpore](https://www.mindspore.cn/install/en) + - [MindSpore](https://www.mindspore.cn/install/) - 如需查看详情，请参见如下资源： - - [MindSpore教程](https://www.mindspore.cn/tutorial/training/zh-CN/master/index.html) - - [MindSpore Python API](https://www.mindspore.cn/doc/api_python/en/master/index.html) + - [MindSpore教程](https://www.mindspore.cn/tutorials/zh-CN/master/index.html) + - [MindSpore Python API](https://www.mindspore.cn/docs/api/en/master/index.html) # 快速入门